Finding feature correspondence is difficult in low textured scenes, which reduces the performance of simultaneous localization and mapping (SLAM). However, lines that are easy to find can solve this problem well. Generally, features cannot be directly matched, it is necessary to perform some calculations on the features to describe the features and obtain descriptors. In this way, the matching of features can be converted into the matching of descriptors. This article mainly introduces a type of line descriptor that is appropriate for SLAM system. The descriptor fully considers the characteristics of the SLAM system and the geometric constrains of line support regions. The advantage of this line descriptor are as follows: (1) It is more suitable for SLAM system; (2) It is invariant to transformation to some degree; (3) It is robust facing extreme scenes.
A Line Descriptor for SLAM (LDFS)
Lect. Notes Electrical Eng.
2021-10-30
13 pages
Article/Chapter (Book)
Electronic Resource
English
A Line Descriptor for SLAM (LDFS)
TIBKAT | 2022
|A Line Descriptor for SLAM (LDFS)
British Library Conference Proceedings | 2022
|ASD-SLAM: A NOVEL ADAPTIVE-SCALE DESCRIPTOR LEARNING FOR VISUAL SLAM
British Library Conference Proceedings | 2020
|